brad/LLM_Engineering_OLD
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Minor updates including pinning datasets version

Browse Source
This commit is contained in:
Edward Donner
2025-07-12 15:26:07 -04:00
parent 8a8493e387
commit a10872469d
17 changed files with 104 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
environment.yml
View File

@@ -17,16 +17,13 @@ dependencies:
- scikit-learn - scikit-learn
- chromadb - chromadb
- jupyter-dash - jupyter-dash
- sentencepiece
- pyarrow - pyarrow
- pip: - pip:
- beautifulsoup4 - beautifulsoup4
- plotly - plotly
- bitsandbytes
- transformers - transformers
- sentence-transformers - sentence-transformers
- datasets - datasets==3.6.0
- accelerate
- openai - openai
- anthropic - anthropic
- google-generativeai - google-generativeai

2
extras/trading/prototype_trader.ipynb
View File

@@ -346,7 +346,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.11" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

16
requirements.txt
View File

@@ -14,18 +14,15 @@ tqdm
openai openai
gradio gradio
langchain langchain
tiktoken langchain-core
langchain-text-splitters
langchain-openai langchain-openai
langchain_experimental langchain-chroma
langchain_chroma langchain-community
langchain[docarray] datasets==3.6.0
datasets
sentencepiece
matplotlib matplotlib
google-generativeai google-generativeai
anthropic anthropic
scikit-learn
unstructured
chromadb chromadb
plotly plotly
jupyter-dash jupyter-dash
@@ -33,9 +30,6 @@ beautifulsoup4
pydub pydub
modal modal
ollama ollama
accelerate
sentencepiece
bitsandbytes
psutil psutil
setuptools setuptools
speedtest-cli speedtest-cli

53
week2/day1.ipynb
View File

@@ -290,12 +290,12 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# If you have access to this, here is the reasoning model o3-mini\n", "# If you have access to this, here is the reasoning model o4-mini\n",
"# This is trained to think through its response before replying\n", "# This is trained to think through its response before replying\n",
"# So it will take longer but the answer should be more reasoned - not that this helps..\n", "# So it will take longer but the answer should be more reasoned - not that this helps..\n",
"\n", "\n",
"completion = openai.chat.completions.create(\n", "completion = openai.chat.completions.create(\n",
" model='o3-mini',\n", " model='o4-mini',\n",
" messages=prompts\n", " messages=prompts\n",
")\n", ")\n",
"print(completion.choices[0].message.content)" "print(completion.choices[0].message.content)"
@@ -308,12 +308,12 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# Claude 3.7 Sonnet\n", "# Claude 4.0 Sonnet\n",
"# API needs system message provided separately from user prompt\n", "# API needs system message provided separately from user prompt\n",
"# Also adding max_tokens\n", "# Also adding max_tokens\n",
"\n", "\n",
"message = claude.messages.create(\n", "message = claude.messages.create(\n",
" model=\"claude-3-7-sonnet-latest\",\n", " model=\"claude-sonnet-4-20250514\",\n",
" max_tokens=200,\n", " max_tokens=200,\n",
" temperature=0.7,\n", " temperature=0.7,\n",
" system=system_message,\n", " system=system_message,\n",
@@ -332,12 +332,12 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# Claude 3.7 Sonnet again\n", "# Claude 4.0 Sonnet again\n",
"# Now let's add in streaming back results\n", "# Now let's add in streaming back results\n",
"# If the streaming looks strange, then please see the note below this cell!\n", "# If the streaming looks strange, then please see the note below this cell!\n",
"\n", "\n",
"result = claude.messages.stream(\n", "result = claude.messages.stream(\n",
" model=\"claude-3-7-sonnet-latest\",\n", " model=\"claude-sonnet-4-20250514\",\n",
" max_tokens=200,\n", " max_tokens=200,\n",
" temperature=0.7,\n", " temperature=0.7,\n",
" system=system_message,\n", " system=system_message,\n",
@@ -408,12 +408,28 @@
")\n", ")\n",
"\n", "\n",
"response = gemini_via_openai_client.chat.completions.create(\n", "response = gemini_via_openai_client.chat.completions.create(\n",
" model=\"gemini-2.5-flash-preview-04-17\",\n", " model=\"gemini-2.5-flash\",\n",
" messages=prompts\n", " messages=prompts\n",
")\n", ")\n",
"print(response.choices[0].message.content)" "print(response.choices[0].message.content)"
] ]
}, },
{
"cell_type": "markdown",
"id": "492f0ff2-8581-4836-bf00-37fddbe120eb",
"metadata": {},
"source": [
"# Sidenote:\n",
"\n",
"This alternative approach of using the client library from OpenAI to connect with other models has become extremely popular in recent months.\n",
"\n",
"So much so, that all the models now support this approach - including Anthropic.\n",
"\n",
"You can read more about this approach, with 4 examples, in the first section of this guide:\n",
"\n",
"https://github.com/ed-donner/agents/blob/main/guides/09_ai_apis_and_ollama.ipynb"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "33f70c88-7ca9-470b-ad55-d93a57dcc0ab", "id": "33f70c88-7ca9-470b-ad55-d93a57dcc0ab",
@@ -583,7 +599,7 @@
"# Have it stream back results in markdown\n", "# Have it stream back results in markdown\n",
"\n", "\n",
"stream = openai.chat.completions.create(\n", "stream = openai.chat.completions.create(\n",
" model='gpt-4o-mini',\n", " model='gpt-4.1-mini',\n",
" messages=prompts,\n", " messages=prompts,\n",
" temperature=0.7,\n", " temperature=0.7,\n",
" stream=True\n", " stream=True\n",
@@ -634,11 +650,11 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# Let's make a conversation between GPT-4o-mini and Claude-3-haiku\n", "# Let's make a conversation between GPT-4.1-mini and Claude-3.5-haiku\n",
"# We're using cheap versions of models so the costs will be minimal\n", "# We're using cheap versions of models so the costs will be minimal\n",
"\n", "\n",
"gpt_model = \"gpt-4o-mini\"\n", "gpt_model = \"gpt-4.1-mini\"\n",
"claude_model = \"claude-3-haiku-20240307\"\n", "claude_model = \"claude-3-5-haiku-latest\"\n",
"\n", "\n",
"gpt_system = \"You are a chatbot who is very argumentative; \\\n", "gpt_system = \"You are a chatbot who is very argumentative; \\\n",
"you disagree with anything in the conversation and you challenge everything, in a snarky way.\"\n", "you disagree with anything in the conversation and you challenge everything, in a snarky way.\"\n",
@@ -774,6 +790,19 @@
"\n", "\n",
"Try creating a 3-way, perhaps bringing Gemini into the conversation! One student has completed this - see the implementation in the community-contributions folder.\n", "Try creating a 3-way, perhaps bringing Gemini into the conversation! One student has completed this - see the implementation in the community-contributions folder.\n",
"\n", "\n",
"The most reliable way to do this involves thinking a bit differently about your prompts: just 1 system prompt and 1 user prompt each time, and in the user prompt list the full conversation so far.\n",
"\n",
"Something like:\n",
"\n",
"```python\n",
"user_prompt = f\"\"\"\n",
" You are Alex, in conversation with Blake and Charlie.\n",
" The conversation so far is as follows:\n",
" {conversation}\n",
" Now with this, respond with what you would like to say next, as Alex.\n",
" \"\"\"\n",
"```\n",
"\n",
"Try doing this yourself before you look at the solutions. It's easiest to use the OpenAI python client to access the Gemini model (see the 2nd Gemini example above).\n", "Try doing this yourself before you look at the solutions. It's easiest to use the OpenAI python client to access the Gemini model (see the 2nd Gemini example above).\n",
"\n", "\n",
"## Additional exercise\n", "## Additional exercise\n",
@@ -824,7 +853,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.12" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

2
week2/day2.ipynb
View File

@@ -568,7 +568,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.12" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

2
week2/day3.ipynb
View File

@@ -301,7 +301,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.11" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

2
week5/community-contributions/day 4 no_langchain/RAG_chat_no_LangChain.ipynb
View File

@@ -386,7 +386,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.11" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

18
week5/community-contributions/docuSeekAI/docuSeekAI.ipynb
View File

@@ -92,10 +92,24 @@
} }
], ],
"metadata": { "metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": { "language_info": {
"name": "python" "codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.12"
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 4
} }

2
week5/day1.ipynb
View File

@@ -256,7 +256,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.11" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

16
week5/day4.5.ipynb
View File

@@ -27,6 +27,20 @@
"import gradio as gr" "import gradio as gr"
] ]
}, },
{
"cell_type": "code",
"execution_count": null,
"id": "94a564ed-5cda-42d9-aada-2a5e85d02d15",
"metadata": {},
"outputs": [],
"source": [
"# install faiss-cpu!\n",
"# Mac users - this may fail if you don't have a recent version of MacOS\n",
"# In which case I recommend you skip this lab -- FAISS is not essential! (Or upgrade MacOS if you wish..)\n",
"\n",
"!pip install faiss-cpu"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
@@ -400,7 +414,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.12" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

16
week6/day1.ipynb
View File

@@ -102,6 +102,18 @@
"%matplotlib inline" "%matplotlib inline"
] ]
}, },
{
"cell_type": "markdown",
"id": "cd6d801e-d195-45fe-898e-495dbcb19d7d",
"metadata": {},
"source": [
"## Load our dataset\n",
"\n",
"In the next cell, we load in the dataset from huggingface.\n",
"\n",
"If this gives you an error like \"trust_remote_code is no longer supported\", then please run this command in a new cell: `!pip install datasets==3.6.0` and then restart the Kernel, and try again."
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
@@ -109,8 +121,6 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# Load in our dataset\n",
"\n",
"dataset = load_dataset(\"McAuley-Lab/Amazon-Reviews-2023\", f\"raw_meta_Appliances\", split=\"full\", trust_remote_code=True)" "dataset = load_dataset(\"McAuley-Lab/Amazon-Reviews-2023\", f\"raw_meta_Appliances\", split=\"full\", trust_remote_code=True)"
] ]
}, },
@@ -429,7 +439,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.12" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

4
week6/day2.ipynb
View File

@@ -119,7 +119,7 @@
"source": [ "source": [
"# Load in the same dataset as last time\n", "# Load in the same dataset as last time\n",
"\n", "\n",
"items = ItemLoader(\"Appliances\").load()" "items = ItemLoader(\"Home_and_Kitchen\").load()"
] ]
}, },
{ {
@@ -624,7 +624,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.12" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

2
week6/day3.ipynb
View File

@@ -918,7 +918,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.12" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

2
week6/day4.ipynb
View File

@@ -398,7 +398,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.11" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

2
week6/lite.ipynb
View File

@@ -427,7 +427,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.12" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

2
week8/day3.ipynb
View File

@@ -227,7 +227,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.11" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,

4
week8/day5.ipynb
View File

@@ -171,7 +171,7 @@
" <span style=\"color:#900;\">If you're not fed up of product prices yet 😂 I've built this out some more!<br/>\n", " <span style=\"color:#900;\">If you're not fed up of product prices yet 😂 I've built this out some more!<br/>\n",
" If you look in my repo <a href=\"https://github.com/ed-donner/tech2ai\">tech2ai</a>, in segment3/lab1 is a neural network implementation of the pricer in pure PyTorch. It does pretty well..<br/>\n", " If you look in my repo <a href=\"https://github.com/ed-donner/tech2ai\">tech2ai</a>, in segment3/lab1 is a neural network implementation of the pricer in pure PyTorch. It does pretty well..<br/>\n",
" And if you look in my repo <a href=\"https://github.com/ed-donner/agentic\">Agentic</a> in the workshop folder is the same Agent project taken further. There's a new version of the PlanningAgent called AutonomousPlanningAgent that uses multiple Tools, and a MessagingAgent that uses claude-3.7 to write texts. The AutonomousPlanningAgent uses the fantastic OpenAI Agents SDK and the mighty MCP protocol from Anthropic.<br/>\n", " And if you look in my repo <a href=\"https://github.com/ed-donner/agentic\">Agentic</a> in the workshop folder is the same Agent project taken further. There's a new version of the PlanningAgent called AutonomousPlanningAgent that uses multiple Tools, and a MessagingAgent that uses claude-3.7 to write texts. The AutonomousPlanningAgent uses the fantastic OpenAI Agents SDK and the mighty MCP protocol from Anthropic.<br/>\n",
" If you're intrigued by Agents and MCP, and would like to learn more, then I also have a <a href=\"https://www.udemy.com/course/the-complete-agentic-ai-engineering-course/?referralCode=1B6986CDBD91FFC3651A\">companion course called the Complete Agentic AI Engineering Course</a> that might interest you (if you haven't had enough of me by now!!)\n", " If you're intrigued by Agents and MCP, and would like to learn more, then I also have a <a href=\"https://edwarddonner.com/2025/05/28/connecting-my-courses-become-an-llm-expert-and-leader/\">companion course called the Complete Agentic AI Engineering Course</a> that might interest you (if you haven't had enough of me by now!!), and also another course for leaders and founders looking to build a valuable business with LLMs.\n",
" </span>\n", " </span>\n",
" </td>\n", " </td>\n",
" </tr>\n", " </tr>\n",
@@ -223,7 +223,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.12" "version": "3.11.13"
} }
}, },
"nbformat": 4, "nbformat": 4,